# TDA-L: Reducing Latency and Memory Consumption of Test-Time Adaptation for Real-Time Intelligent Sensing

## TL;DR

TDA-L improves real-time intelligent sensing by reducing latency and memory use during test-time adaptation of vision-language models.

## Contribution

TDA-L introduces Low-Rank Adaptation to reduce computational overhead in test-time adaptation without training.

## Key findings

- TDA-L achieves lower latency and memory consumption compared to existing methods.
- It maintains accuracy while improving throughput for real-time applications.
- Experiments on seven benchmarks confirm its efficiency and robustness.

## Abstract

Vision–language models learn visual concepts from the supervision of natural language. It can significantly enhance the generalizability of real-time intelligent sensing, such as analyzing camera-captured real-time images for visually impaired users. However, adapting vision–language models to distribution shifts at test time, caused by several factors such as lighting or weather changes, remains challenging. In particular, most existing test-time adaptation methods rely on gradient-based fine-tuning and backpropagation, making them computationally expensive and unsuitable for real-time applications. To address this challenge, the Training-Free Dynamic Adapter (TDA) has recently been introduced as a lightweight alternative that uses a dynamic key–value cache and pseudo-label refinement for test-time adaptation without backpropagation. Building on this, we propose TDA-L, a new framework that integrates Low-Rank Adaptation (LoRA) to reduce the size of feature representations and related computational overhead at test time using pre-learned low-rank matrices. TDA-L applies LoRA transformations to both query and cached features during inference, cost-efficiently improving robustness to distribution shifts while maintaining the training-free nature of TDA. Experimental results on seven benchmarks show that TDA-L maintains accuracy but achieves lower latency, less memory consumption, and higher throughput, making it well-suited for AI-based real-time sensing.